Introduction
Materials and Methods
Results
Discussion
Conclusion
Outline
Introduction
- Project aim
Introduction
- Data set of Rural People from Bangladesh with or without T1-Diabetes (source: https://www.kaggle.com/sabbir1996/dataset-of-diabetes-type1)
- Contains 306 data points and 22 variables
- Classify people with T1 diabetes and explore important variables for T1 diabetes
Materials and Methods
Obtain data set
Data Wrangling
Exploratory Data Analysis
Analysis and PCA Modeling
Logistic Regression model and Machine Learning
Shiny App
Working collaboratively using RStudio Cloud and Github
Materials and Methods
- Include flow chart diagram
Results: Exploratory Data Analysis
Results: EDA (contd.)
Results: EDA (contd.)
Results: EDA (contd.)
Results: Analysis and Modeling
Results: Analysis and Modeling
Data is well seperated so classification seems to be feasible.
Results: Analysis and Modeling
Logistic regression done using tidymodels
Perform binary classification
Parameters: other_diseases, height, weight, famHist2DBin, famHist1DBin
Assessing the predictive ability of the model
Results: Analysis and Modeling
Results: Analysis and Modeling
Link (source = https://hcehlers.shinyapps.io/DiaPredict/)
Discussion
Limited by the data set: location, race and habitat of source data limit the global usability of the model
Unique observation: Height seems to impact the likelihood of diabetes
The accuracy of our model can be increased with added parameters and data points
Scope for cross platforming and integrated studies
Conclusion
It was feasible to do data analysis and obtain biological insights about our data set
We conclude that height and weight are important indicators of T1 diabetes
We expected family history to be more important
More descriptive data would have made it easier to conclude and test hypotheses